INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     değildir
    -0.09
    keen
    -0.08
     enn
    -0.08
    рот
    -0.08
     olmay
    -0.08
    'ad
    -0.08
     ಜಿಲ್ಲಾ
    -0.08
    812
    -0.08
     cape
    -0.08
     الرسمية
    -0.08
    POSITIVE LOGITS
     large
    0.09
    large
    0.08
    .large
    0.08
     મોટા
    0.07
     hence
    0.07
     મોટી
    0.07
     मोठ
    0.07
     Object
    0.07
     oer
    0.07
     watching
    0.07
    Act Density 0.074%

    No Known Activations